"""system_embeddings — a charter becomes an ANSWER, not just a filter (#4251)

Revision ID: 0107
Revises: 0106
Create Date: 2026-09-21

A System's `description` is a charter: several hundred words saying what
belongs in that area and what does not. It is the answer to "which part of
this codebase does X live in", and there was no semantic path to it.
`list_systems` enumerates and `search(system_id=…)` uses a System as a FILTER
over notes — so a System could narrow a search and could never be the answer
to one, and an agent asking where a record belonged had to read every charter
or guess.

The fourth sibling of note_embeddings (0067), rule_embeddings (0089) and
milestone_embeddings (0102), and for the same reason note 3163 gives about the
third: the row could be shared, the search cannot. "Where does this belong?"
is a different question from "what prior art is there?", and no note or rule
search can answer it, because a charter is not a note.

The vectors are DERIVED: nothing is backfilled here, the startup backfill
writes them.
"""
import sqlalchemy as sa
from alembic import op

revision = "0107"
down_revision = "0106"
branch_labels = None
depends_on = None

# Matches its three siblings — bge-small-en-v1.5, 384-dim.
_EMBEDDING_DIM = 384


def upgrade() -> None:
    op.create_table(
        "system_embeddings",
        sa.Column(
            "system_id", sa.Integer(),
            sa.ForeignKey("systems.id", ondelete="CASCADE"), primary_key=True,
        ),
        sa.Column("chunk_index", sa.Integer(), primary_key=True),
        sa.Column("chunk_text", sa.Text(), nullable=False),
        sa.Column("chunker_version", sa.Integer(), nullable=False),
        sa.Column(
            "updated_at", sa.DateTime(timezone=True), nullable=False,
            server_default=sa.text("now()"),
        ),
    )
    # Raw DDL for the vector column, as 0067, 0089 and 0102 do: the type comes
    # from the pgvector extension, not SQLAlchemy's type system.
    op.execute(
        f"ALTER TABLE system_embeddings ADD COLUMN embedding vector({_EMBEDDING_DIM}) NOT NULL"
    )
    op.execute(
        """
        CREATE INDEX ix_system_embeddings_embedding_hnsw
            ON system_embeddings
         USING hnsw (embedding vector_cosine_ops)
        """
    )


def downgrade() -> None:
    op.execute("DROP INDEX IF EXISTS ix_system_embeddings_embedding_hnsw")
    op.drop_table("system_embeddings")